1.1 Colors

# devtools::install_cran(c("RColorBrewer",
#                          "ggplot2",
#                          "ggcorrplot"))

library(RColorBrewer)
library(ggplot2)
library(ggcorrplot)
# Code source: https://rstudio-pubs-static.s3.amazonaws.com/177286_826aed2f00794640b301aeb42533c6f1.html

ggplot(
  diamonds,
  aes(carat, price)
) +
  geom_point(aes(color = cut)) +
  scale_color_brewer(
    type = "div",
    palette = 4,
    direction = 1
  ) +
  xlab("Carats") +
  ylab("Price") +
  ggtitle("Diamonds")

ggplot(
  diamonds,
  aes(carat,
    price,
    color = cut
  )
) +
  geom_point() +
  scale_color_brewer(
    type = "div",
    palette = "PRGn",
    direction = 1
  ) +
  xlab("Carats") +
  ylab("Price") +
  ggtitle("Diamonds")

1.2 Correlation heat map

library(ggcorrplot)
# code source: http://www.sthda.com/english/wiki/ggcorrplot-visualization-of-a-correlation-matrix-using-ggplot2

data(mtcars)
corr <- round(cor(mtcars), 1)
p.mat <- cor_pmat(mtcars)
ggcorrplot(corr,
  hc.order = TRUE,
  type = "lower", p.mat = p.mat
)

1.3 Combined plots

library(ggplot2)
library(gridExtra)
# Code source: http://felixfan.github.io/ggplot2-cheatsheet/

# generate some data
set.seed(999)
xvar <- c(rnorm(1500, mean = -1), rnorm(1500, mean = 1.5))
yvar <- c(rnorm(1500, mean = 1), rnorm(1500, mean = 1.5))
zvar <- as.factor(c(rep(1, 1500), rep(2, 1500)))
xy <- data.frame(xvar, yvar, zvar)


# placeholder plot - prints nothing at all
empty <- ggplot() + geom_point(aes(1, 1), colour = "white") + theme(
  plot.background = element_blank(),
  panel.grid.major = element_blank(), panel.grid.minor = element_blank(),
  panel.border = element_blank(), panel.background = element_blank(), axis.title.x = element_blank(),
  axis.title.y = element_blank(), axis.text.x = element_blank(), axis.text.y = element_blank(),
  axis.ticks = element_blank()
)

# scatterplot of x and y variables
scatter <- ggplot(xy, aes(xvar, yvar)) + geom_point(aes(color = zvar)) + scale_color_manual(values = c(
  "orange",
  "purple"
)) + theme(legend.position = c(1, 1), legend.justification = c(
  1,
  1
))

# marginal density of x - plot on top
plot_top <- ggplot(xy, aes(xvar, fill = zvar)) + geom_density(alpha = 0.5) +
  scale_fill_manual(values = c("orange", "purple")) + theme(legend.position = "none")

# marginal density of y - plot on the right
plot_right <- ggplot(xy, aes(yvar, fill = zvar)) + geom_density(alpha = 0.5) +
  coord_flip() + scale_fill_manual(values = c("orange", "purple")) + theme(legend.position = "none")

# arrange the plots together, with appropriate height and width for each row
# and column
grid.arrange(plot_top, empty, scatter, plot_right, ncol = 2, nrow = 2, widths = c(
  4,
  1
), heights = c(1, 4))

1.4 Time Series

library(ggplot2)
library(lubridate)
theme_set(theme_bw())

df <- economics_long[economics_long$variable %in% c("psavert", "uempmed"), ]
df <- df[lubridate::year(df$date) %in% c(1967:1981), ]

# labels and breaks for X axis text
brks <- df$date[seq(1, length(df$date), 12)]
lbls <- lubridate::year(brks)

# plot
ggplot(df, aes(x = date)) +
  geom_line(aes(y = value, col = variable)) +
  labs(
    title = "Time Series of Returns Percentage",
    subtitle = "Drawn from Long Data format",
    caption = "Source: Economics",
    y = "Returns %",
    color = NULL
  ) + # title and caption
  scale_x_date(labels = lbls, breaks = brks) + # change to monthly ticks and labels
  scale_color_manual(
    labels = c("psavert", "uempmed"),
    values = c("psavert" = "#00ba38", "uempmed" = "#f8766d")
  ) + # line color
  theme(
    axis.text.x = element_text(angle = 90, vjust = 0.5, size = 8), # rotate x axis text
    panel.grid.minor = element_blank()
  ) # turn off minor grid

1.5 Calendar Heatmap

library(ggplot2)
library(plyr)
library(scales)
library(zoo)

# code source:# http://margintale.blogspot.in/2012/04/ggplot2-time-series-heatmaps.html

df <- read.csv("https://raw.githubusercontent.com/selva86/datasets/master/yahoo.csv")
df$date <- as.Date(df$date) # format date
df <- df[df$year >= 2012, ] # filter reqd years

# Create Month Week
df$yearmonth <- as.yearmon(df$date)
df$yearmonthf <- factor(df$yearmonth)
df <- ddply(df, .(yearmonthf), transform, monthweek = 1 + week - min(week)) # compute week number of month
df <- df[, c("year", "yearmonthf", "monthf", "week", "monthweek", "weekdayf", "VIX.Close")]
head(df)

# Plot
ggplot(df, aes(monthweek, weekdayf, fill = VIX.Close)) +
  geom_tile(colour = "white") +
  facet_grid(year ~ monthf) +
  scale_fill_gradient(low = "red", high = "green") +
  labs(
    x = "Week of Month",
    y = "",
    title = "Time-Series Calendar Heatmap",
    subtitle = "Yahoo Closing Price",
    fill = "Close"
  )

1.6 Spatial data

library(tidyverse)
library(maps)

# Code Source: https://mgimond.github.io/ES218/Week12a.html

# first plot a simple map of the us
cnty <- map_data("county")
ggplot(cnty, 
       aes(long, lat, group = group)) +
  geom_polygon(aes(fill = region), 
               show.legend = FALSE, 
               colour = rgb(1, 1, 1, 0.2)) +
  coord_map("bonne", param = 45) +
  theme_void()

#  get data on median income per person
df <- read_csv("http://mgimond.github.io/ES218/Data/Income_education.csv")
df1 <- df %>% select(subregion = County, 
                     region = State, 
                     B20004001)

# create lookup table between state names/abbreviations
st <- tibble(region = tolower(state.name), 
                 State = tolower(state.abb))
st <- bind_rows(st, 
                tibble(region = "district of columbia", 
                               State = "dc"))

# join census data to counties
df1 <- df %>%
  inner_join(st, by = "State") %>%
  mutate(subregion = tolower(County)) %>%
  select(subregion, 
         region, 
         B20004001)

cnty.df1 <- inner_join(cnty, 
                       df1, 
                       by = c("region", "subregion"))

# map income distribution
ggplot(cnty.df1, 
       aes(long, 
           lat, 
           group = group)) +
  geom_polygon(aes(fill = B20004001), 
               colour = rgb(1, 1, 1, 0.2)) +
  coord_quickmap()

1.7 Interactive plots

library(plotly)


d <- diamonds[sample(nrow(diamonds), 1000), ]
p <- ggplot(data = d, 
            aes(x = carat, 
                y = price)) +
  geom_point(aes(text = paste("Clarity:", clarity)), 
             size = 4) +
  geom_smooth(aes(colour = cut, 
                  fill = cut)) + 
  facet_wrap(~ cut)

(gg <- ggplotly(p))

2.1 Basic components of a ggplot

We’ll use the mpg data package included with ggplot to run through some examples of ggplot capabilities. Here we create the most basic of plots.

# get information about the mpg data package
?mpg

# view mpg data frame
mpg

# make a scatterplot (GEOM_FUNCTION= geom_point) of engine displacement vs. highway miles per gallon.
# The ggplot statement establishes a coordinate system and data= tells what data to plot. the geom_point specifies how data are visualized.

ggplot(data = mpg) +
  geom_point(mapping = aes(x = displ, 
                           y = hwy))

## geometric objects

A geom is the geometrical object that a plot uses to represent data – lines, bars, points are all geometrical objects. Here we make some simple adjustments to use different objects to represent the data

# lots of options for geometric objects -- simply type geom_ and view the pull down menu to see what these are

# another option for looking at continuous vs. continuous is geometric smooth (uses a loess function)
ggplot(data = mpg) +
  geom_smooth(mapping = aes(x = displ, 
                            y = hwy))

#  ggplot works by layering objects. Here we can layer the points and smoothed lines.  Note that if we want to apply the same aesthetic mappings to all geometric objects in the plot, we can specify theses in the ggplot statement to avoid redundancy. Any additional aesthetics specified for the object will override this.
ggplot(data = mpg, 
       mapping = aes(x = displ, 
                                 y = hwy)) +
  geom_point() +
  geom_smooth()

# for a discrete vs. continuous variable
ggplot(data = mpg) +
  geom_boxplot(mapping = aes(x = trans, 
                             y = hwy))

# for a single continuous variable
ggplot(data = mpg) +
  geom_histogram(mapping = aes(x = displ), 
                 binwidth = 0.5)

# for a single discrete variable
ggplot(data = mpg) +
  geom_bar(mapping = aes(x = trans))

## aesthetic mappings

Aesthetics are visual properties of the objects in the plot – for example, size, shape, color

# here we add a color aesthetic to visualize a third variable, vehicle class.ggplot automatically adds a legend here.

ggplot(data = mpg) +
  geom_point(mapping = aes(x = displ, 
                           y = hwy, 
                           color = class))

# some other options -- some are more appropriate/useful than others
ggplot(data = mpg) +
  geom_point(mapping = aes(x = displ, 
                           y = hwy, 
                           alpha = class))

ggplot(data = mpg) +
  geom_point(mapping = aes(x = displ, 
                           y = hwy, 
                           shape = class))

ggplot(data = mpg) +
  geom_point(mapping = aes(x = displ, 
                           y = hwy, 
                           size = class))

ggplot(data = mpg) +
  geom_smooth(mapping = aes(x = displ, 
                            y = hwy, 
                            linetype = drv))

## Faceting

Faceting is one place that ggplot really stands out. It provides another way to easily add additional variables to your plot.

# facets can be created based on on variable like this:
ggplot(data = mpg) +
  geom_point(mapping = aes(x = displ, 
                           y = hwy)) +
  facet_wrap(~ class, nrow = 2)

# or by two variables, using facet_grid

ggplot(data = mpg) +
  geom_point(mapping = aes(x = displ, 
                           y = hwy)) +
  facet_grid(drv ~ cyl)

2.2 statistics mappings

We saw above in the geom_smooth plots that ggplot uses the loess smoothing function as a default statistic. Statistics are implicit in many of the plot types but can also be specified explicitly, depending on the context. The algorithm used to calculate new values for a graph is called a stat.

# for a bar plot, a 'count' statistic is automatically calculated from the data
ggplot(data = mpg) +
  geom_bar(mapping = aes(x = trans))

# for a geom_smooth plot, we can explicitly specify the statistical method using method = "lm", "glm", "gam", "loess", etc.

ggplot(data = mpg, 
       mapping = aes(x = displ, 
                                 y = hwy)) +
  geom_point() +
  geom_smooth(method = "lm")

2.3 Position mappings

The third component of mappings is the position. This is especially useful for bar charts

# the default here gives us a stacked bar chart
ggplot(mpg, mapping = aes(x = fl, 
                          fill = drv)) +
  geom_bar()

# but we can position the bars in differnt ways to get different types of bar charts
ggplot(mpg, mapping = aes(x = fl, 
                          fill = drv)) +
  geom_bar(position = "dodge")

ggplot(mpg, mapping = aes(x = fl, 
                          fill = drv)) +
  geom_bar(position = "fill")

# or jitter the position of points to reveal overlapping points
ggplot(data = mpg) +
  geom_point(mapping = aes(x = displ, 
                           y = hwy), 
             position = "jitter")

2.4 Coordinate systems

Plots can readily be switched from one coordinate system to another –xy positions can be flipped or wrapped into a polar coordinate system

bar <- ggplot(data = mpg) +
  geom_bar(
    mapping = aes(x = fl, 
                  fill = drv),
    show.legend = FALSE,
    width = 1
  )
bar

bar + coord_flip()

bar + coord_polar()